Foundational Models Defining a New Era in Vision: A Survey and Outlook
Vision systems to see and reason about the compositional nature of visualscenes are fundamental to understanding our world. The complex relationsbetween objects and their locations, ambiguities, and variations in thereal-world environment can be better described in human language, naturallygover…
Muhammad Awais
Tracking Anything in High Quality
Visual object tracking is a fundamental video task in computer vision.Recently, the notably increasing power of perception algorithms allows theunification of single/multiobject and box/mask-based tracking. Among them, theSegment Anything Model (SAM) attracts much attention. In this report, wepr…
Jiawen ZhuUniversal and Transferable Adversarial Attacks on Aligned Language Models
Because “out-of-the-box” large language models are capable of generating agreat deal of objectionable content, recent work has focused on aligning thesemodels in an attempt to prevent undesirable generation. While there has beensome success at circumventing these measures -- so-called “jailbreaks…
Andy ZouTowards Generalist Biomedical AI
Medicine is inherently multimodal, with rich data modalities spanning text,imaging, genomics, and more. Generalist biomedical artificial intelligence (AI)systems that flexibly encode, integrate, and interpret this data at scale canpotentially enable impactful applications ranging from scientific…
Tao TuAligning Large Language Models with Human: A Survey
Large Language Models (LLMs) trained on extensive textual corpora haveemerged as leading solutions for a broad array of Natural Language Processing(NLP) tasks. Despite their notable performance, these models are prone tocertain limitations such as misunderstanding human instructions, generatingp…
Yufei Wang